scAClc: A Multi-Objective Adaptive Clustering Framework for Single-Cell Transcriptomics via Contrastive and Resolution-Aware Representation Learning

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Consistently outperformed six state-of-the-art methods

• Primary Outcome: Clustering accuracy across multiple evaluation metrics

• Nnt Or Sensitivity: Superior performance across silhouette score, adjusted rand index, and normalized mutual information

• Confidence Interval: Not reported

Clinical Application

High feasibility with open-source implementation and standard computational requirements Relevant to Australian genomics research initiatives, cancer research programs, and precision medicine efforts supported by Medical Research Future Fund Researchers and clinicians using single-cell RNA sequencing for disease characterization, drug discovery, and precision medicine

Abstract

Single-cell RNA sequencing (scRNA-seq) enables whole-transcriptomic profiling at single-cell resolution, facilitating the construction of virtual cell representations that capture the full spectrum of cellular identities. Realizing this goal hinges on accurate clustering, which remains challenging due to data sparsity, high dimensionality, noise, and the need to specify cluster numbers a priori. We propose scAClc, a novel clustering framework featuring multiobjective optimization and adaptive resolution discovery, designed to address these limitations through three key innovations. First, a Hierarchical Gene Relevance Module integrates global gene variability with local neighborhood-specific signals to eliminate redundancy while retaining biologically informative features. Second, an Anchor-Centered Contrastive Learning Module adaptively selects representative anchors to guide embedding learning, promoting compact intracluster structure and clear intercluster separation. Third, based on the robust low-dimensional embedding, we propose a Self-Adaptive Resolution Discovery Module to automatically infer the number of clusters by jointly modeling intra- and intercluster distances. Extensive experiments on 15 real scRNA-seq data sets demonstrate that scAClc consistently outperforms six state-of-the-art methods across multiple evaluation metrics. Ablation studies further confirmed the complementary contributions of each module. In addition, interpretability analysis effectively mitigates the "black box" nature of clustering models and sheds light on the biological mechanisms underlying cell clustering. The source code is publicly available at https://github.com/scAClc/scAClc.

References

1. 1.Zheng, Y., Jin, R., Zhang, Y., Cheng, Y., & Wang, Y. (2026). scAClc: A Multi-Objective Adaptive Clustering Framework for Single-Cell Transcriptomics via Contrastive and Resolution-Aware Representation Learning. Analytical Chemistry. https://doi.org/10.1021/acs.analchem.5c06601